bert_uncased_L-2_H-128_A-2-mlm-multi-emails-hq (BERT-tiny)

This model is a fine-tuned version of google/bert_uncased_L-2_H-128_A-2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.0981
  • Accuracy: 0.4728

Model description

BERT-tiny fine-tuned on email data for eight epochs.

Intended uses & limitations

  • this is mostly a test

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 0.0003
  • train_batch_size: 8
  • eval_batch_size: 2
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.05
  • num_epochs: 8.0
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
3.8974 0.99 141 3.5129 0.4218
3.7009 1.99 282 3.3295 0.4452
3.5845 2.99 423 3.2219 0.4589
3.4976 3.99 564 3.1618 0.4666
3.4356 4.99 705 3.1002 0.4739
3.4493 5.99 846 3.1028 0.4746
3.4199 6.99 987 3.0857 0.4766
3.4086 7.99 1128 3.0981 0.4728

Framework versions

  • Transformers 4.27.0.dev0
  • Pytorch 2.0.0.dev20230129+cu118
  • Datasets 2.8.0
  • Tokenizers 0.13.1
Downloads last month
42
Safetensors
Model size
4.42M params
Tensor type
I64
·
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for postbot/bert_uncased_tiny-multi-emails-hq

Finetuned
(50)
this model